Pure javascript cross-platform module to extract text from PDFs.
A quick fix for the pdf-parse library - it works now!
Pure javascript cross-platform module to extract texts from PDFs.
npm install pdf-parse``js
const fs = require('fs');
const pdf = require('pdf-parse');
let dataBuffer = fs.readFileSync('path to PDF file...');
pdf(dataBuffer).then(function(data) {
// number of pages
console.log(data.numpages);
// number of rendered pages
console.log(data.numrender);
// PDF info
console.log(data.info);
// PDF metadata
console.log(data.metadata);
// PDF.js version
// check https://mozilla.github.io/pdf.js/getting_started/
console.log(data.version);
// PDF text
console.log(data.text);
});
`
Exception Handling
js
const fs = require('fs');
const pdf = require('pdf-parse');let dataBuffer = fs.readFileSync('path to PDF file...');
pdf(dataBuffer).then(function(data) {
// use data
})
.catch(function(error){
// handle exceptions
})
`Extend
* v1.0.9 and above break pagerender callback changelog
* If you need another format like json, you can change page render behaviour with a callback
* Check out https://mozilla.github.io/pdf.js/js
// default render callback
function render_page(pageData) {
//check documents https://mozilla.github.io/pdf.js/
let render_options = {
//replaces all occurrences of whitespace with standard spaces (0x20). The default value is false.
normalizeWhitespace: false,
//do not attempt to combine same line TextItem's. The default value is false.
disableCombineTextItems: false
} return pageData.getTextContent(render_options)
.then(function(textContent) {
let lastY, text = '';
for (let item of textContent.items) {
if (lastY == item.transform[5] || !lastY){
text += item.str;
}
else{
text += '\n' + item.str;
}
lastY = item.transform[5];
}
return text;
});
}
let options = {
pagerender: render_page
}
let dataBuffer = fs.readFileSync('path to PDF file...');
pdf(dataBuffer,options).then(function(data) {
//use new format
});
`Options
js
const DEFAULT_OPTIONS = {
// internal page parser callback
// you can set this option, if you need another format except raw text
pagerender: render_page,
// max page number to parse
max: 0,
//check https://mozilla.github.io/pdf.js/getting_started/
version: 'v1.10.100'
}
`
$3
If you need another format except raw text. $3
Max number of page to parse. If the value is less than or equal to 0, parser renders all pages. $3
check pdf.js*
*
*
*
* >default version is v1.10.100
>mozilla.github.io/pdf.js
Test
* or npm test`
* A Guide for First-Timers
* How to create a merge request
* Check Contributing Guide